Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    explanation text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.70
     ہے۔
    0.66
     wskaz
    0.63
     grudnia
    0.61
     Север
    0.60
     налази
    0.59
     ਗਿਆ
    0.59
     گئی۔
    0.59
    hört
    0.57
     kogu
    0.57
    POSITIVE LOGITS
    the
    0.83
    ва
    0.81
    ك
    0.64
    ה
    0.61
    of
    0.56
    ان
    0.55
    )",
    0.55
    w
    0.55
    ка
    0.54
    why
    0.54
    Act Density 0.062%

    No Known Activations